Using Automated Infant Posture Recognition to Reduce SIDS Risk

According to the CDC, approximately 3500 infants die annually in the United States from sleep related infant deaths, such as Sudden Infant Death Syndrome (SIDS). My project aims to reduce the extrinsic risk factors of SIDS by initiating an automatic alert when an infant’s posture is high-risk (as considered by the American Academy of Pediatrics). My hypothesis is PoseNet can be used to identify infant body parts and a machine learning (ML) model could effectively recognize infant lying posture.

I downloaded pictures of infants in various lying positions and produced about 50,000 video frames. On each frame, I ran PoseNet and generated generated coordinates and a confidence score for different body parts. Then, I progressively added more features, such as angles and distances between certain body parts. Using this dataset, I built a geometric algorithm and a machine learning (ML) model. After refining the most accurate ML model, the accuracy improved to 96.67% with a root mean square error of 0.072.

I incorporated this model into my “SIDS Pose Recognition” application. With the model and the app, both my hypothesis proved to be correct. With my user-friendly app, caregivers would immediately receive an alert when an infant’s position is unsafe or high-risk for SIDS.